Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agentic coding notes

danluu.com

Post reply on HN
Print view View original

71–80 of 99 posts

Re: Agentic coding notes

#71

Post by zarzavat »

stingraycharles wrote: post #21
danielbln wrote: post #19

Earlier quoted context omitted.

And I've been quite impressed. Opus talks the talk, Fable walks the walk.

I don’t understand what these comments add to the discussion, you always see these and it’s just noise at this point.

Every metric becomes a target (Goodhart's law). Also, the plural of anecdote is not data.

The subjective anecdotes from HN users matter because they are not data and are much harder to game. Not impossible to game, always be aware of users with low karma, but more difficult than gaming a benchmark.

Re: Agentic coding notes

#72

Post by ornornor »

zapnuk wrote: post #39

There is a reasone we use left and right margin/padding. This blog is quite unreadable for 27/32" monitors.

The point of a wide monitor for me is to have two 720 wide windows side by side, not a single gigantic 1440 window with impossibly long lines.

Re: Agentic coding notes

#73

Post by stingraycharles »

zarzavat wrote: post #71
stingraycharles wrote: post #21

Earlier quoted context omitted.

I don’t understand what these comments add to the discussion, you always see these and it’s just noise at this point.

Every metric becomes a target (Goodhart's law). Also, the plural of anecdote is not data. The subjective anecdotes from HN users matter because they are not data and are much harder to game. Not impossible to game, always be aware of users with low karma, but more difficult than gaming a benchmark.

But they’re not at all meaningful after a certain point, because they’re not even attempting to explain why it works well for them. It’s just noise like this.

Re: Agentic coding notes

#75

Post by gregwebs »

duckmysick wrote: post #38

I'd like to highlight a different part of the article: > In general, when I talk to software folks about testing, I'm coming from such a different place that they immediately look at me like I'm an alien, so let's talk about how we tested at this hardware company I worked for, Centaur, which informs my biases about how I like to work. Some of the things that we did that were or are unorthodox in the software world ar…

No code review by default goes against actual established evidence (there is little of this for software development practice) that code review is the best way to find defects.

I always get the impression from using hardware and other anecdotes like this that it is rare for hardware companies to know how to do software development well because their core competency is hardware. In fairness, it is uncommon for software companies to know how to do software development well.

Every form of testing has its value when done well and they are using several forms that most software developers don't use- probably helps make up for the lack of code review and unit tests. But if they incorporated code review and unit tests their software would likely be even higher quality.

Property based testing is amazing, but it won't provide full coverage. Regression suites are amazing, but generally the most expensive form of testing in terms of time to write and maintain tests and time to run them.

Today AI can crank out unit tests so its silly not to have them.

Re: Agentic coding notes

#76

Post by baq »

layer8 wrote: post #58
zapnuk wrote: post #39

There is a reasone we use left and right margin/padding. This blog is quite unreadable for 27/32" monitors.

There’s a reason not to maximize your browser windows. How do you handle HN threads on that monitor?

Why would you work with anything other than maximized windows unless you have a super ultra wide display?

Re: Agentic coding notes

#77

Post by baq »

cognitiveinline wrote: post #54

It's really coming down to "Do we want to subscribe to a human with a salary of many ~$10000(s) ", or "Do we spend 100(s)$ on an AI subscription" Even with it's issues, the latest models are going to disrupt the labor economics.

It’s going to even out on both eventually, the diffusion will be painful though.

Re: Agentic coding notes

#78

Post by baq »

eru wrote: post #42
zarzavat wrote: post #13

Earlier quoted context omitted.

API prices are the new normal. I doubt that prices will drop to the level of the subsidized subscriptions any time soon. Usage is growing exponentially but capacity cannot. There is no reason for them to waste their capacity on subscription users if they can sell that same capacity to API users. Like with Uber and Lyft, the low prices were a fight for market share, but now they have successfully captured that market…

I suspect subscriptions will stay. But you will see more and more roadblocks that the 'barely goes to the gym' user barely notices, but that the power user will chafe under. I make that prediction, because the people who pay for subscriptions but only use them moderately at best are truly profitable.

The $200 sub is the new free tier, has been for a while now.

Re: Agentic coding notes

#79

Post by steveklabnik »

vidarh wrote: post #49
zarzavat wrote: post #4

Fable changes the game yet again, because it's API-only. You're not likely to want to run Fable in a loop any more than you want to take a bunch of dollar bills and light them on fire. Every invocation of Fable has to be intentional, its context carefully managed. I feel like a babysitter.

I just had Fable run overnight in a loop, and it fixed ~150 compiler crashing bugs that Opus had kept deferring. I wouldn't start with Fable - when I use burndown loops I tend to include instructions to document progress and set aside anything that turns out to be harder than expected, and solve the easy stuff first. When a model runs out of easy stuff and start struggling to make progress on what is left, I can let…

I had fable running in a loop overnight last night, finding bugs. It found a heap overflow. That triggered its safety guards, which converted the thing to opus, leaving opus to run the rest of the night, wasting my precious time with Fable.

Oh well, it was pretty funny, all things considered.

Re: Agentic coding notes

#80

Post by ballsac »

fooster wrote: post #59
embedding-shape wrote: post #37

Earlier quoted context omitted.

> melted away in the face of massive context sizes If only. There is a huge difference between "Gives good responses/can easily spot things within N context size" and "Technically works but sucks within N context size", almost all models basically become cave-people once you go beyond 50% of the "supported" context size, meaning while they may technically work with 1 million output tokens, those last 500K tokens are…

I don’t find that to be true?

[dead]
Post reply on HN